Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    News/commentary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onical
    -0.06
    &uuml
    -0.06
     developers
    -0.06
     minValue
    -0.06
     noise
    -0.06
     worry
    -0.06
    альных
    -0.06
    `
    -0.06
     rentals
    -0.05
     Comput
    -0.05
    POSITIVE LOGITS
     Amerikan
    0.07
    ("""↵
    0.07
     添加
    0.07
     saddened
    0.07
    "/>↵↵
    0.06
    :function
    0.06
    ::|
    0.06
    ===
    0.06
     Dipl
    0.06
     Benn
    0.06
    Act Density 0.123%

    No Known Activations